Update website datasource settings
curl --request PATCH \
--url http://localhost:8080/crawl/{id} \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"display_name": "<string>",
"page_limit": 2500,
"exclude_paths": [
"<string>"
],
"include_paths": [
"<string>"
],
"crawl_interval_hours": 4503599627370508,
"restricted_to_channels": [],
"auth": {
"type": "basic",
"username": "<string>",
"password": "<string>"
}
}
'import requests
url = "http://localhost:8080/crawl/{id}"
payload = {
"display_name": "<string>",
"page_limit": 2500,
"exclude_paths": ["<string>"],
"include_paths": ["<string>"],
"crawl_interval_hours": 4503599627370508,
"restricted_to_channels": [],
"auth": {
"type": "basic",
"username": "<string>",
"password": "<string>"
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.patch(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'PATCH',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
display_name: '<string>',
page_limit: 2500,
exclude_paths: ['<string>'],
include_paths: ['<string>'],
crawl_interval_hours: 4503599627370508,
restricted_to_channels: [],
auth: {type: 'basic', username: '<string>', password: '<string>'}
})
};
fetch('http://localhost:8080/crawl/{id}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_PORT => "8080",
CURLOPT_URL => "http://localhost:8080/crawl/{id}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "PATCH",
CURLOPT_POSTFIELDS => json_encode([
'display_name' => '<string>',
'page_limit' => 2500,
'exclude_paths' => [
'<string>'
],
'include_paths' => [
'<string>'
],
'crawl_interval_hours' => 4503599627370508,
'restricted_to_channels' => [
],
'auth' => [
'type' => 'basic',
'username' => '<string>',
'password' => '<string>'
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "http://localhost:8080/crawl/{id}"
payload := strings.NewReader("{\n \"display_name\": \"<string>\",\n \"page_limit\": 2500,\n \"exclude_paths\": [\n \"<string>\"\n ],\n \"include_paths\": [\n \"<string>\"\n ],\n \"crawl_interval_hours\": 4503599627370508,\n \"restricted_to_channels\": [],\n \"auth\": {\n \"type\": \"basic\",\n \"username\": \"<string>\",\n \"password\": \"<string>\"\n }\n}")
req, _ := http.NewRequest("PATCH", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.patch("http://localhost:8080/crawl/{id}")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"display_name\": \"<string>\",\n \"page_limit\": 2500,\n \"exclude_paths\": [\n \"<string>\"\n ],\n \"include_paths\": [\n \"<string>\"\n ],\n \"crawl_interval_hours\": 4503599627370508,\n \"restricted_to_channels\": [],\n \"auth\": {\n \"type\": \"basic\",\n \"username\": \"<string>\",\n \"password\": \"<string>\"\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("http://localhost:8080/crawl/{id}")
http = Net::HTTP.new(url.host, url.port)
request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"display_name\": \"<string>\",\n \"page_limit\": 2500,\n \"exclude_paths\": [\n \"<string>\"\n ],\n \"include_paths\": [\n \"<string>\"\n ],\n \"crawl_interval_hours\": 4503599627370508,\n \"restricted_to_channels\": [],\n \"auth\": {\n \"type\": \"basic\",\n \"username\": \"<string>\",\n \"password\": \"<string>\"\n }\n}"
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"url": "<string>",
"display_name": "<string>",
"status": "<string>",
"page_limit": 123,
"exclude_paths": [
"<string>"
],
"include_paths": [
"<string>"
],
"crawl_interval_hours": 123,
"restricted_to_channels": [
"web"
],
"last_crawl_started_at": "2023-11-07T05:31:56Z",
"last_crawl_completed_at": "2023-11-07T05:31:56Z",
"error_message": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z",
"auth_configured": true,
"auth_type": "basic"
}{
"statusCode": 123,
"message": "<string>",
"error": "<string>"
}Crawl
Update website datasource settings
Update configuration for a website datasource. Use when driving the website crawler programmatically — queueing crawls, inspecting jobs, and curating indexed pages.
PATCH
/
crawl
/
{id}
Update website datasource settings
curl --request PATCH \
--url http://localhost:8080/crawl/{id} \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"display_name": "<string>",
"page_limit": 2500,
"exclude_paths": [
"<string>"
],
"include_paths": [
"<string>"
],
"crawl_interval_hours": 4503599627370508,
"restricted_to_channels": [],
"auth": {
"type": "basic",
"username": "<string>",
"password": "<string>"
}
}
'import requests
url = "http://localhost:8080/crawl/{id}"
payload = {
"display_name": "<string>",
"page_limit": 2500,
"exclude_paths": ["<string>"],
"include_paths": ["<string>"],
"crawl_interval_hours": 4503599627370508,
"restricted_to_channels": [],
"auth": {
"type": "basic",
"username": "<string>",
"password": "<string>"
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.patch(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'PATCH',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
display_name: '<string>',
page_limit: 2500,
exclude_paths: ['<string>'],
include_paths: ['<string>'],
crawl_interval_hours: 4503599627370508,
restricted_to_channels: [],
auth: {type: 'basic', username: '<string>', password: '<string>'}
})
};
fetch('http://localhost:8080/crawl/{id}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_PORT => "8080",
CURLOPT_URL => "http://localhost:8080/crawl/{id}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "PATCH",
CURLOPT_POSTFIELDS => json_encode([
'display_name' => '<string>',
'page_limit' => 2500,
'exclude_paths' => [
'<string>'
],
'include_paths' => [
'<string>'
],
'crawl_interval_hours' => 4503599627370508,
'restricted_to_channels' => [
],
'auth' => [
'type' => 'basic',
'username' => '<string>',
'password' => '<string>'
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "http://localhost:8080/crawl/{id}"
payload := strings.NewReader("{\n \"display_name\": \"<string>\",\n \"page_limit\": 2500,\n \"exclude_paths\": [\n \"<string>\"\n ],\n \"include_paths\": [\n \"<string>\"\n ],\n \"crawl_interval_hours\": 4503599627370508,\n \"restricted_to_channels\": [],\n \"auth\": {\n \"type\": \"basic\",\n \"username\": \"<string>\",\n \"password\": \"<string>\"\n }\n}")
req, _ := http.NewRequest("PATCH", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.patch("http://localhost:8080/crawl/{id}")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"display_name\": \"<string>\",\n \"page_limit\": 2500,\n \"exclude_paths\": [\n \"<string>\"\n ],\n \"include_paths\": [\n \"<string>\"\n ],\n \"crawl_interval_hours\": 4503599627370508,\n \"restricted_to_channels\": [],\n \"auth\": {\n \"type\": \"basic\",\n \"username\": \"<string>\",\n \"password\": \"<string>\"\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("http://localhost:8080/crawl/{id}")
http = Net::HTTP.new(url.host, url.port)
request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"display_name\": \"<string>\",\n \"page_limit\": 2500,\n \"exclude_paths\": [\n \"<string>\"\n ],\n \"include_paths\": [\n \"<string>\"\n ],\n \"crawl_interval_hours\": 4503599627370508,\n \"restricted_to_channels\": [],\n \"auth\": {\n \"type\": \"basic\",\n \"username\": \"<string>\",\n \"password\": \"<string>\"\n }\n}"
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"url": "<string>",
"display_name": "<string>",
"status": "<string>",
"page_limit": 123,
"exclude_paths": [
"<string>"
],
"include_paths": [
"<string>"
],
"crawl_interval_hours": 123,
"restricted_to_channels": [
"web"
],
"last_crawl_started_at": "2023-11-07T05:31:56Z",
"last_crawl_completed_at": "2023-11-07T05:31:56Z",
"error_message": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z",
"auth_configured": true,
"auth_type": "basic"
}{
"statusCode": 123,
"message": "<string>",
"error": "<string>"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
The website datasource ID
Pattern:
^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$Body
application/json
Required range:
1 <= x <= 5000Required range:
24 <= x <= 9007199254740991Available options:
active, paused Available options:
web, email, phone_voice, slack, sms, whatsapp, instagram, messenger, api, web_voice, twitter, twitter_mentions, app_review, internal - Option 1
- Option 2
- Option 3
- Option 4
Show child attributes
Show child attributes
Response
Default Response
Pattern:
^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$Channels this datasource is restricted to. Empty = available on all channels.
Available options:
web, email, phone_voice, slack, sms, whatsapp, instagram, messenger, api, web_voice, twitter, twitter_mentions, app_review, internal Whether optional Firecrawl site auth is configured. Secrets are never returned.
Configured auth type, or null when auth is not set.
Available options:
basic, bearer, cookie, headers Was this page helpful?